EP4530682A1 - Traitement sonique in situ en temps réel de trou de forage - Google Patents

Traitement sonique in situ en temps réel de trou de forage Download PDF

Info

Publication number
EP4530682A1
EP4530682A1 EP24203022.9A EP24203022A EP4530682A1 EP 4530682 A1 EP4530682 A1 EP 4530682A1 EP 24203022 A EP24203022 A EP 24203022A EP 4530682 A1 EP4530682 A1 EP 4530682A1
Authority
EP
European Patent Office
Prior art keywords
data
training
dispersion
neural network
sonic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP24203022.9A
Other languages
German (de)
English (en)
Inventor
Lin Liang
Ting LEI
Yixin Wang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Services Petroliers Schlumberger SA
Schlumberger Technology BV
Original Assignee
Services Petroliers Schlumberger SA
Schlumberger Technology BV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Services Petroliers Schlumberger SA, Schlumberger Technology BV filed Critical Services Petroliers Schlumberger SA
Publication of EP4530682A1 publication Critical patent/EP4530682A1/fr
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
    • G01V1/40—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging
    • G01V1/44—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging using generators and receivers in the same well
    • G01V1/48—Processing data
    • G01V1/50—Analysing data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
    • G01V1/40—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging
    • G01V1/44—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging using generators and receivers in the same well
    • G01V1/48—Processing data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B2200/00—Special features related to earth drilling for obtaining oil, gas or water
    • E21B2200/22—Fuzzy logic, artificial intelligence, neural networks or the like
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V2200/00—Details of seismic or acoustic prospecting or detecting in general
    • G01V2200/10—Miscellaneous details
    • G01V2200/16—Measure-while-drilling or logging-while-drilling
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V2210/00—Details of seismic processing or analysis
    • G01V2210/50—Corrections or adjustments related to wave propagation
    • G01V2210/58—Media-related
    • G01V2210/582—Dispersion

Definitions

  • aspects of the disclosure relate to sonic wellbore data processing. More specifically, aspects of the disclosure provide for the interpretation of borehole sonic dispersion data using data-driven machine learning based techniques.
  • systems and methods described herein provide techniques for processing sonic dispersion data in-situ in substantially real-time.
  • systems and methods described herein are configured to train a neural network model using training sonic dispersion data to map the training sonic dispersion data to one or more dispersion modal curves of a plurality of dispersion modal curves, to receive real-time sonic dispersion data from an acoustic logging tool in substantially real-time while the acoustic logging tool is deployed within a wellbore extending through a geological formation, and to utilize the trained neural network model to analyze the real-time sonic dispersion data in substantially real-time while the acoustic logging tool is deployed within the wellbore extending through the geological formation to predict a dispersion modal curve of the plurality of dispersion modal curves to which the real-time sonic dispersion data relates and/or directly calculate a parameter of the geological formation.
  • connection As used herein, the terms “connect,” “connection,” “connected,” “in connection with,” and “connecting” are used to mean “in direct connection with” or “in connection with via one or more elements”; and the term “set” is used to mean “one element” or “more than one element.” Further, the terms “couple,” “coupling,” “coupled,” “coupled together,” and “coupled with” are used to mean “directly coupled together” or “coupled together via one or more elements.” As used herein, the terms “up” and “down,” “uphole” and “downhole”, “upper” and “lower,” “top” and “bottom,” and other like terms indicating relative positions to a given point or element are utilized to more clearly describe some elements.
  • these terms relate to a reference point as the surface from which drilling operations are initiated as being the top (e.g., uphole or upper) point and the total depth along the drilling axis being the lowest (e.g., downhole or lower) point, whether the well (e.g., wellbore, borehole) is vertical, horizontal or slanted relative to the surface.
  • the term “interval” with respect to coiled tubing (CT) pipe is used to mean a particular axial portion along an axial length of the CT pipe.
  • a priori data is used to mean data that is determined based on theoretical deduction rather than empirical measurement.
  • real time may be used interchangeably and are intended to described operations (e.g., computing operations) that are performed without any human-perceivable interruption between operations.
  • data relating to the systems described herein may be collected, transmitted, and/or used in control computations in "substantially real time” such that data readings, data transfers, and/or data processing steps occur once every second, once every 0.1 second, once every 0.01 second, or even more frequent, during operations of the systems (e.g., while the systems are operating).
  • the terms “automatic”, “automatically”, and “automated” are intended to describe operations that are performed or caused to be performed, for example, by a data processing system (i.e., solely by the data processing system, without human intervention).
  • the term “approximately equal to” may be used to mean values that are relatively close to each other (e.g., within 5%, within 2%, within 1%, within 0.5 %, or even closer, of each other).
  • FIG. 1 illustrates a graph 10 of logging-while-drilling (LWD) quadrupole dispersion data, where several modes can be excited simultaneously.
  • LWD logging-while-drilling
  • FIG. 1 illustrates the following sets of sonic dispersion data:
  • the borehole quadrupole mode 14 is the desired mode to be inverted for formation shear slowness. Traditionally, proper frequency filters need to be set manually in order to label the correct mode and avoid mislabeling other contamination modes, such as the collar quadrupole mode 16 or the higher-order quadrupole mode 22.
  • MLADI machine learning enabled automatic dipole interpretation
  • MLAQI machine learning enabled automatic quadrupole interpretation
  • the embodiments described herein include methods for labeling various modes from borehole sonic slowness-frequency data and estimate formation slowness.
  • the embodiments described herein enable a fully automated solution with high computational efficiency, which makes real-time in-situ processing of borehole sonic measurement possible.
  • the data-driven machine learning (ML) techniques described herein may be deployed to wellsite or downhole for real-time data processing.
  • the embodiments described herein include a framework for interpretation of borehole sonic dispersion data using data-driven ML-based approaches.
  • training datasets from two possible sources may be generated.
  • First, application of MLADI and MLAQI methods on field data processing will naturally create substantial volumes of labeled data (e.g., pairing dispersion data with dispersion modes labeled by MLADI and MLAQI).
  • These two types of labeled data may be used either separately or in combination to train neural network models. These models may map dispersion data to modal dispersion much more efficiently than MLADI and MLAQI solutions.
  • the embodiments described herein may complete data processing within seconds using just a single CPU, making it suitable for deployment on a computer at a wellsite or even downhole.
  • the trained model and processing algorithms described herein may be further implemented on FPGA or ASIC for even better performance.
  • FIG. 2 depicts a schematic diagram of a system 30 for processing sonic and ultrasonic wellbore measurements.
  • FIG. 2 illustrates surface equipment 32 above a geological formation 34.
  • a drilling operation has previously been carried out to drill a wellbore 36.
  • cement 38 has been used to seal an annulus 40 (i.e., the space between the wellbore 36 and casing joints 42 and collars 44).
  • casing joints 42 are coupled together by the casing collars 44 to stabilize the wellbore 36.
  • the casing joints 42 represent lengths of conductive pipe, which may be formed from steel or similar materials.
  • the casing joints 42 each may include an externally threaded (male thread form) connection at each end.
  • a corresponding internally threaded (female thread form) connection in the casing collars 44 may connect two nearby casing joints 42. Coupled in this way, the casing joints 42 may be assembled to form a casing string 54 to a suitable length and specification for the wellbore 36.
  • the casing joints 42 and/or collars 44 may be made of carbon steel, stainless steel, or other suitable materials to withstand a variety of forces, such as collapse, burst, and tensile failure, as well as chemically aggressive fluid.
  • the surface equipment 32 may carry out various well logging operations to detect conditions of the wellbore 36, as described in greater detail herein.
  • the well logging operations may measure parameters of the geological formation 34 (e.g., resistivity or porosity) and/or the wellbore 36 (e.g., temperature, pressure, fluid type, or fluid flowrate). As will be discussed in greater detail below, some of these measurements may be obtained at various points in the design, drilling, and completion of the well, and may be used to evaluate properties of the geological formation 34 and/or the wellbore 36.
  • an acoustic logging tool 46 may obtain at least some of these measurements.
  • the example of FIG. 2 shows the acoustic logging tool 46 being conveyed through the wellbore 36 by a cable 48.
  • a cable 48 may be a mechanical cable, an electrical cable, or an electro-optical cable that includes a fiber line protected against the harsh environment of the wellbore 36.
  • the acoustic logging tool 46 may be conveyed using any other suitable conveyance, such as coiled tubing.
  • the acoustic logging tool 46 may obtain measurements of amplitude and variable density from sonic acoustic waves, acoustic impedance from ultrasonic waves, and/or flexural attenuation and velocity from the third interface echo. The availability of these independent measurements may be used to increase accuracy and confidence in the well and/or formation evaluation and interpretation made possible by the acoustic logging tool 46.
  • the acoustic logging tool 46 may be deployed inside the wellbore 36 by the surface equipment 32, which may include a vehicle 50 and a deploying system such as a drilling rig 52. Data related to the geological formation 34 or the wellbore 36 gathered by the acoustic logging tool 46 may be transmitted to the surface, and/or stored in the acoustic logging tool 46 for later processing and analysis.
  • the vehicle 50 may be fitted with or may communicate with a computer and software to perform data collection and analysis.
  • FIG. 2 also schematically illustrates a magnified view of a portion of the wellbore 36.
  • the acoustic logging tool 46 may obtain acoustic measurements relating to the presence of solids or liquids behind the casing 42.
  • the surface equipment 32 may pass the measurements as data 56 to a data processing system 58 that includes a processor 60, memory 62, storage 64, and/or a display 66.
  • the data 56 may be processed by a similar data processing system 58 at any other suitable location (e.g., remote data center).
  • the data processing system 58 may collect the data 56 and determine one or more indices and indicators that, as described in greater detail herein, may objectively indicate various properties of the geological formation 34, as well as within the wellbore 36 itself. Additionally or alternatively, the data processing system 58 may correlate a variety of data obtained throughout the creation of the well (e.g., design, drilling, logging, well completion, etc.) that may assist in the evaluation of the wellbore 36 and/or the geological formation 34. Namely, the processor 60, using instructions stored in the memory 62 and/or storage 64, may calculate the indicators and/or indices and/or may collect and correlate the other data into the well and/or formation evaluation.
  • the memory 62 and/or the storage 64 of the data processing system 58 may be any suitable article of manufacture that can store the instructions.
  • the memory 62 and/or the storage 64 may be ROM, random-access memory (RAM), flash memory, an optical storage medium, or a hard disk drive, to name a few examples.
  • the display 66 may be any suitable electronic display that can display the logs, indices, and/or indicators relating to the wellbore 36 and/or the geological formation 34.
  • FIG. 3 depicts an example operation of the acoustic logging tool 46 in the wellbore 36.
  • a transducer 72 in the acoustic logging tool 46 may emit acoustic waves 74 out toward the casing 42 and the geological formation 34. Reflected acoustic waves 76, 78 may correspond to interfaces at the casing 42, the cement 38, and the geological formation 34, respectively.
  • the acoustic logging tool 46 may use any suitable number of different techniques, including measurements of amplitude and variable density from sonic acoustic waves, acoustic impedance from ultrasonic waves, and/or flexural attenuation and velocity from the third interface echo.
  • a sonic source e.g., a monopole sonic source
  • a cased-hole e.g., double casing hole
  • an array of sonic sensing elements may be used to detect reflected acoustic waves corresponding to various interfaces (e.g., interfaces at the casing 42, the cement 38, and the geological formation 34, respectively).
  • MLADI ML-assisted method
  • WL wireline
  • MLAQI LWD borehole sonic quadrupole interpretation
  • neural network models are trained on synthetic data (generated through modeling such as mode search) to map from model parameters to dispersion data (i.e., slowness-frequency domain).
  • waveforms may first be transformed to dispersion data.
  • a combination of clustering algorithms and inversion processes are used to automatically label and invert the corresponding dispersion mode (e.g., dipole mode and quadrupole mode).
  • dispersion mode e.g., dipole mode and quadrupole mode.
  • the data processing time can range from minutes to hours, contingent on the data volume being processed, due at least in part to the computationally intensive nature of the processing.
  • the embodiments described herein provide data-driven ML-based methods to directly map from the sonic dispersion data to various dispersion modes (e.g., such as dipole and quadrupole, and the other dispersion modes illustrated in FIG.1 ) and simultaneously obtain the most sensitive formation parameters such as slowness.
  • the embodiments described herein include training a neural network model that directly maps from sonic dispersion data 80 to a dispersion modal curve 82, as illustrated in FIG. 4 .
  • the first source of the training dataset can be from field data processing (e.g., from field data collected by an acoustic logging tool 46). In practice, many borehole sonic measurements may be processed using MLAQI/MLADI or other methods, from which a large volume of labeled data may be obtained for machine learning.
  • the second source of the training dataset can be from numerical modeling. A variety of model scenarios can be created and simulated by numerical solvers to generate synthetic sonic data with natural labeling.
  • sonic dispersion data 80 may be used as an input, and the dispersion modal curve 82 and/or slowness values may be used as outputs.
  • the training dataset may be pre-processed before being used for machine learning.
  • a quality control (QC) threshold may be chosen to filter out those data with a low QC score.
  • FIG .5 shows one data sample with a relatively high QC score.
  • some additional thresholds may be applied to remove some scattered points to suppress noise. For example, as illustrated in FIG. 5 , certain dispersion data points 80 that scatter around with low coherence may be removed from consideration to obtain a converted image 84.
  • the slowness and frequency may be normalized using pre-defined lower and upper bounds, as illustrated in FIG. 5 .
  • the normalized dispersion data 80 may be converted to a two-dimensional (2D) image 84 or, indeed, may be transformed into any type of image 84 (e.g., a binary image, an image with more color scales, and so forth).
  • image 84 e.g., a binary image, an image with more color scales, and so forth.
  • other attributes such as amplitude in the dispersion plot may be ignored and the dispersion data 80 may be converted into a binary image (i.e., black and white, as with the illustrated converted image 84).
  • the next step is to train a neural network model by feeding the pre-processed labeled dataset (e.g., the converted image 84 illustrated in FIG. 5 ) as an input array 86, as illustrated in the neural network model training workflow 88 of FIG. 6 .
  • a variety of neural network structures 90 may be selected for this ML problem.
  • Converted 2D images 84 may be transformed to different types of arrays as inputs, depending on the particular neural network structure 90 utilized.
  • the neural network model parameters may be optimized to ensure output matching the labeled dispersion modal curve 82 or variant (e.g., a true formation shear slowness could be concatenated to the one-dimensional (1D) array of dispersion modal curve 82).
  • a fully connected neural network model 90 may be used, but it can be replaced by other structures such as a convolutional neural network model 90, and so forth.
  • dispersion data 80 can be transformed into an image 84, either a binary image, or an image with more color scales.
  • the 2D image 84 i.e., a 2D input array
  • the output may be a 1D array representing the dispersion modal curve 82 that is composed of slowness for pre-defined frequencies.
  • the trained neural network model 90 may be used for real-time field data processing.
  • FIG. 7 illustrates a general high-level workflow 92 of utilizing a trained neural network model 90 and
  • FIG. 8 illustrates results when applied to one sample data set.
  • sonic waveforms 94 may be collected (e.g., using an acoustic logging tool 46) in substantially real-time and real-time dispersion data 96 (e.g., similar to the training dispersion data 80 discussed above) may be extracted from the sonic waveforms 94 and converted into a 2D image 98 (e.g., similar to the training 2D images 84 discussed above) or other type of image, which may be fed into the trained neural network model 90 to predict a dispersion modal curve 100 and/or directly calculate a slowness.
  • the predicted dispersion modal curve 100 may, in turn, be used to determine certain parameters of the geological formation 34 including, but not limited to, slowness.
  • this workflow 92 may be executed on different infrastructures, including CPU on wellsite or downhole computers, FPGA or ASIC.
  • other data processing systems e.g., FPGA or ASIC integrated into an acoustic logging tool 46
  • the data processing system 58 may perform some of the data processing functions described herein while other data processing systems (e.g., FPGA or ASIC integrated into an acoustic logging tool 46) may perform other data processing functions described herein.
  • the data processing system 58 may perform the training of the neural network model 90 described herein while other data processing systems (e.g., FPGA or ASIC integrated into an acoustic logging tool 46) may analyze real-time data based on the trained neural network model 90, as also described herein.
  • other data processing systems e.g., FPGA or ASIC integrated into an acoustic logging tool 46
  • FIG. 9 illustrates an example method 102 of utilizing the in-situ real-time sonic dispersion data processing techniques described herein.
  • the method 102 may include training a neural network model 90 using training sonic dispersion data 80 to map the training sonic dispersion data 80 to one or more dispersion modal curves 82 of a plurality of dispersion modal curves 82 (block 104).
  • the method 102 may also include receiving real-time sonic dispersion data 96 from an acoustic logging tool 46 in substantially real-time while the acoustic logging tool 46 is deployed within a wellbore 36 extending through a geological formation 34 (block 106).
  • the method 102 may further include utilizing the trained neural network model 90 to analyze the real-time sonic dispersion data 96 in substantially real-time while the acoustic logging tool 46 is deployed within the wellbore 36 extending through the geological formation 34 to predict a dispersion modal curve 82 of the plurality of dispersion modal curves 82 (as a predicted dispersion modal curve 100) to which the real-time sonic dispersion data 96 relates and/or directly calculate at least one parameter (e.g., compressional slowness, shear slowness, anisotropy, radial alteration, and so forth) of the geological formation 34 (block 108).
  • a parameter e.g., compressional slowness, shear slowness, anisotropy, radial alteration, and so forth
  • the predicted dispersion modal curve 100 may, in turn, be used to determine certain parameters of the geological formation 34 including, but not limited to, compressional slowness, shear slowness, anisotropy, radial alteration, and so forth.
  • training the neural network model 90 using training sonic dispersion data 80 may include converting the training sonic dispersion data 80 into an image 84, and training the neural network model 90 using the image 84 as an input array 86.
  • the image 84 may be a 2D image 84 of the training sonic dispersion data 80.
  • the method 102 may also include pre-processing the training sonic dispersion data 80 prior to training the neural network model 90 using training sonic dispersion data 80.
  • pre-processing the training sonic dispersion data 80 may include filtering out one or more training sonic dispersion data sets 80 having a quality control (QC) score lower than a QC threshold.
  • pre-processing the training sonic dispersion data 80 may include normalizing parameters of the training sonic dispersion data 80 using pre-defined lower and upper bounds.
  • the method 102 may include utilizing the trained neural network model 90 to interpret multiple modes associated with the plurality of dispersion modal curves 82 simultaneously. In addition, in certain embodiments, the method 102 may include utilizing the trained neural network model 90 to interpret compressional slowness and shear slowness for the geological formation 34 simultaneously. In addition, in certain embodiments, the at least one parameter of the geological formation 34 may include shear slowness for the geological formation 34, and the method 102 may include using the formation shear slowness as an initial guess for machine learning enabled automatic dipole interpretation (MLADI) analysis or machine learning enabled automatic quadrupole interpretation (MLAQI) analysis for further refinement of the shear slowness for the geological formation 34.
  • MLADI machine learning enabled automatic dipole interpretation
  • MLAQI machine learning enabled automatic quadrupole interpretation
  • the plurality of dispersion modal curves 82 may include a Stoneley mode 12, a borehole quadrupole mode 14, a collar quadrupole mode 16, a modeled dispersion curve 18 of a borehole quadrupole mode for shear slowness output, a shear head wave or pseudo-Rayleigh mode 20, a dispersive second-order quadrupole mode 22, a compressional head wave 24, and a frequency spectra for monopole 26 or quadrupole 28.
  • the solution described herein needs minimal computational resource enabling real-time data processing at downhole conditions, which is extremely attractive for an LWD scenario due to limited bandwidth on data transmission during drilling.
  • the framework may be extended to other modes such Stoneley, dipole, pseudo-Rayleigh, leaky-P, and so forth (e.g., as discussed above with respect to FIG. 1 ) and applied to interpret multiple modes simultaneously.
  • the framework may also be extended to interpret compressional and shear slowness simultaneously.
  • the solution may be used to obtain the formation shear slowness, which can then be used as an initial guess for MLADI/MLAQI analysis for further refinement. This hybrid solution is much faster than typical MLADI/MLAQI analysis while maintaining good accuracy.

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geophysics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Remote Sensing (AREA)
  • Acoustics & Sound (AREA)
  • Geology (AREA)
  • Environmental & Geological Engineering (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Geophysics And Detection Of Objects (AREA)
EP24203022.9A 2023-09-29 2024-09-26 Traitement sonique in situ en temps réel de trou de forage Pending EP4530682A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202363586763P 2023-09-29 2023-09-29
US202463632845P 2024-04-11 2024-04-11

Publications (1)

Publication Number Publication Date
EP4530682A1 true EP4530682A1 (fr) 2025-04-02

Family

ID=92926333

Family Applications (1)

Application Number Title Priority Date Filing Date
EP24203022.9A Pending EP4530682A1 (fr) 2023-09-29 2024-09-26 Traitement sonique in situ en temps réel de trou de forage

Country Status (3)

Country Link
US (1) US20250110250A1 (fr)
EP (1) EP4530682A1 (fr)
CN (1) CN119785799A (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180196156A1 (en) * 2017-01-10 2018-07-12 Reeves Wireline Technologies Limited Method of and Apparatus for Carrying Out Acoustic Well Logging
US20220244419A1 (en) * 2019-06-14 2022-08-04 Schlumberger Technology Corporation Machine learning enhanced borehole sonic data interpretation

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180196156A1 (en) * 2017-01-10 2018-07-12 Reeves Wireline Technologies Limited Method of and Apparatus for Carrying Out Acoustic Well Logging
US20220244419A1 (en) * 2019-06-14 2022-08-04 Schlumberger Technology Corporation Machine learning enhanced borehole sonic data interpretation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LIANG LIN ET AL: "Automated interpretation and quality control of logging-while-drilling quadrupole sonic dispersion in anisotropic formations", SECOND INTERNATIONAL MEETING FOR APPLIED GEOSCIENCE & ENERGY, 15 August 2022 (2022-08-15), pages 267 - 271, XP093239352, DOI: 10.1190/image2022-3751154.1 *

Also Published As

Publication number Publication date
US20250110250A1 (en) 2025-04-03
CN119785799A (zh) 2025-04-08

Similar Documents

Publication Publication Date Title
US10858933B2 (en) Method for analyzing cement integrity in casing strings using machine learning
US10345465B2 (en) Resonance-based inversion of acoustic impedance of annulus behind casing
US10995606B2 (en) Well integrity analysis using sonic measurements over depth interval
US11378707B2 (en) Third interface echo (TIE) detection from flexural data for gas/liquid annulus discrimination
US11220897B2 (en) Evaluating casing cement using automated detection of clinging compression wave (P) arrivals
WO2016187240A1 (fr) Procédé d'analyse de l'intégrité du ciment dans des puits tubés à l'aide de la diagraphie acoustique
US20210325558A1 (en) Methods and systems for processing slowness values from borehole sonic data
EP3701124A1 (fr) Procédés d'analyse de l'intégrité du ciment dans des espaces annulaires d'un puits multitubé à l'aide d'un apprentissage automatique
US11675100B2 (en) Mitigation of fiber optic cable coupling for distributed acoustic sensing
Bose et al. Acoustic evaluation of annulus b barriers through tubing for plug and abandonment job planning
WO2020117235A1 (fr) Procédés et systèmes de traitement d'ondes dispersives de trou de forage avec une analyse d'apprentissage machine basée sur la physique
US10317555B2 (en) Method of minimizing tool response for downhole logging operations
EP4530682A1 (fr) Traitement sonique in situ en temps réel de trou de forage
NO20250301A1 (en) Characterizing coupling quality using amplitude spectra
WO2024226107A1 (fr) Estimation de propriétés de matériau en utilisant des modèles proxy
US12497888B2 (en) Channel detection system and method
BR102024019893A2 (pt) Processamento sônico de poço inacabado em tempo real in-situ
WO2019152450A1 (fr) Systèmes et procédés d'évaluation de lenteur en cisaillement de formations
Lei et al. Sonic Data Classification Using Supervised Machine-Learning Approach
US20250217631A1 (en) Deep Learning System for Casing Centralization Estimation Through Pulse-Echo TIE Interference
US20240369731A1 (en) Fast approach for acoustic impedance computation through dimension expansion
US20240221065A1 (en) Bidding proposal editing system
US20250284023A1 (en) Fast approach for dispersion curve stacking, visualization and calibration
WO2024107822A1 (fr) Systèmes et procédés de traitement acoustique au niveau d'un dispositif d'accès
WO2024228725A1 (fr) Estimation de filtre à facteur de qualité rapide dans une inversion de forme d'onde acoustique

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20250620

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20251022